© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7723
    Prev
    Next
    INDEX
    Explanations

    the letters 'I', 'c', and 'o' sometimes with other nearby letters, in various contexts including math, code, and general text

    oai_token-act-pair · gemini-2.0-flash

    Technical contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referenties
    -0.69
    !")
    
    -0.67
    .",
    
    -0.66
     MessageBoxIcon
    -0.64
     Roskov
    -0.63
    "),
    
    -0.63
    .")
    
    -0.62
    Gruss
    -0.62
    !");
    -0.61
    ^(@)
    -0.61
    POSITIVE LOGITS
     o
    0.77
     O
    0.75
     disambiguazione
    0.66
    sizeCache
    0.65
    didSet
    0.59
    ー
    0.57
     surla
    0.57
    ANDS
    0.56
     О
    0.56
     فريبيس
    0.54
    Activations Density 1.083%

    No Known Activations